© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103134
    Prev
    Next
    INDEX
    Explanations

    cooperative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    1.13
    ations
    1.04
    ively
    1.01
    aneously
    0.96
    ently
    0.95
    iks
    0.92
     one
    0.89
    ها
    0.88
    fection
    0.87
    apping
    0.86
    POSITIVE LOGITS
    d
    1.47
    2
    1.44
    า
    1.32
    يا
    1.29
    ة
    1.27
    to
    1.26
    ب
    1.21
    ോ
    1.21
    ه
    1.20
    ST
    1.16
    Activations Density 0.001%

    No Known Activations